---
last_updated: 2026-11-20
source_url: https://opper.ai/alibaba/qwen3-6-27b
title: "Qwen 3.6 27B by Alibaba"
description: "Qwen3.6-27B by Alibaba: 27B open-weight multimodal model with strong agentic coding (77.2 SWE-bench Verified) and reasoning across 262K context."
---

# Qwen 3.6 27B

By [Alibaba](https://opper.ai/alibaba).

Released 22 Apr 2026, 1 days after [HappyHorse 1.0 Text-to-Video](https://opper.ai/alibaba/happyhorse-1-0-t2v) · [Announcement](https://qwen.ai/blog?id=qwen3.6-27b) · [All Alibaba releases](https://opper.ai/model-releases/alibaba)

Qwen3.6-27B is an open-weight 27 billion parameter dense multimodal model focused on agentic coding and reasoning. It uses 64 layers with a hybrid attention structure that mixes Gated DeltaNet linear attention with standard gated attention, and supports a 262,144 token native context window, extensible toward roughly one million tokens with YaRN scaling.

Reported scores include SWE-bench Verified 77.2, AIME 2026 94.1, and VideoMME 87.7, reflecting strength in coding, math reasoning, and video understanding. It handles text, image, and video inputs and offers both thinking and non-thinking modes in one checkpoint.

The model excels at frontend workflows and repository-level code reasoning, supporting tool calling and complex multimodal problem solving for agentic applications.

## Available routes

Qwen 3.6 27B runs on 4 different routes through the Opper gateway. Prices are per 1M tokens. In the EU it is served by Greenference. [See every Qwen model hosted in the EU](https://opper.ai/models/eu/qwen). One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=qwen3.6-27b.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepInfra](https://opper.ai/provider/deepinfra) | `deepinfra/Qwen/Qwen3.6-27B` | US (United States) | Yes | No | $0.32 | $3.20 | Input price |
| [DeepInfra](https://opper.ai/provider/deepinfra), Flex | `deepinfra:flex/Qwen/Qwen3.6-27B` | US (United States) | Yes | No | $0.26 | $2.56 | $0.26 |
| [DeepInfra](https://opper.ai/provider/deepinfra), Priority | `deepinfra:priority/Qwen/Qwen3.6-27B` | US (United States) | Yes | No | $0.48 | $4.80 | $0.48 |
| [Greenference](https://opper.ai/provider/greenference) | `greenference/qwen3.6-27b` | EU | Yes | No | $0.15 | $1.35 | $0.07 |
| [Groq](https://opper.ai/provider/groq) | `groq/qwen/qwen3.6-27b` | US (United States) | Yes | No | $0.60 | $3.00 | $0.30 |
| [Novita](https://opper.ai/provider/novita) | `novita/qwen/qwen3.6-27b` | US (United States) | Yes | No | $0.60 | $3.60 | Input price |

## Key info

- Model id: `qwen3.6-27b` (routes across DeepInfra, Novita)
- Input: Text, Image, Video
- Output: Text
- Features: Reasoning, Tools, Structured output
- Context window: 262K
- Max output: 262K
- Input price: $0.32 per 1M tokens
- Output price: $3.20 per 1M tokens
- Released: 22 Apr 2026
- EU residency available on Greenference
- US residency available on DeepInfra, Groq and Novita
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Qwen 3.6 27B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### DeepInfra — United States

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-19.

### Greenference — EU

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Caching: Content cached for replay
- Subprocessor access: Subprocessors may read content
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-09-21.

### Groq — United States

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-16.

### Novita — United States

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-15.

## Best for

Where Qwen 3.6 27B ranks among the models on Opper with a score for each use case (0 to 100).

- [Agents](https://opper.ai/models?use=agents): 5.5 (Terminal-Bench 4.0 and AutomationBench)

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/qwen3-6-27b)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #168 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 57 tok/s
- Intelligence Index (previous version): 21.4

### Coding

- Terminal-Bench 4.0: 0%
- SciCode: 43%

### Agentic & knowledge work

- AutomationBench: 11%
- GDPval: 25%
- GDP.pdf: 11%
- Briefcase (Elo): 816
- Terminal-Bench Hard: 35%
- τ²-Bench Telecom: 94%

### Science & reasoning

- Humanity's Last Exam: 23%
- GPQA Diamond: 84%
- Long-context reasoning: 77%

### Knowledge

- MMMU-Pro: 75%

### Math & instruction following

- IFBench: 68%

## Get started

Call Qwen 3.6 27B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen 3.6 27B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Qwen 3.6 27B
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "qwen3.6-27b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "qwen3.6-27b",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "qwen3.6-27b",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.6-27b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Qwen 3.6 27B in your apps

Pick your tool to see how to run it on Qwen 3.6 27B through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/qwen3-6-27b)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/qwen3-6-27b)
- [Codex](https://opper.ai/apps/codex/qwen3-6-27b)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/qwen3-6-27b)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/qwen3-6-27b)
- [Aider](https://opper.ai/apps/aider/qwen3-6-27b)
- [Goose](https://opper.ai/apps/goose/qwen3-6-27b)
- [Droid](https://opper.ai/apps/droid/qwen3-6-27b)
- [OpenCode](https://opper.ai/apps/opencode/qwen3-6-27b)
- [Pi](https://opper.ai/apps/pi/qwen3-6-27b)
- [OpenClaw](https://opper.ai/apps/openclaw/qwen3-6-27b)
- [Hermes](https://opper.ai/apps/hermes/qwen3-6-27b)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/qwen3-6-27b)
- [OmniRoute](https://opper.ai/apps/omniroute/qwen3-6-27b)
- [Cursor](https://opper.ai/apps/cursor/qwen3-6-27b)
- [Cline](https://opper.ai/apps/cline/qwen3-6-27b)
- [Continue](https://opper.ai/apps/continue/qwen3-6-27b)
- [Kilo Code](https://opper.ai/apps/kilo-code/qwen3-6-27b)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/qwen3-6-27b)
- [Zed](https://opper.ai/apps/zed/qwen3-6-27b)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/qwen3-6-27b)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/qwen3-6-27b)
- [n8n](https://opper.ai/apps/n8n/qwen3-6-27b)
- [LibreChat](https://opper.ai/apps/librechat/qwen3-6-27b)
- [Open WebUI](https://opper.ai/apps/open-webui/qwen3-6-27b)
- [See all apps](https://opper.ai/apps)

## Other models from Alibaba

- [Qwen4-Max](https://opper.ai/alibaba/qwen4-max)
- [Qwen3.8 Max](https://opper.ai/alibaba/qwen3-8-max)
- [Qwen3.8 27B](https://opper.ai/alibaba/qwen3-8-27b)
- [Qwen3.8-2.4T-A95B](https://opper.ai/alibaba/qwen3-8-2-4t-a95b)
- [Qwen3.8 Flash-Next](https://opper.ai/alibaba/qwen3-8-flash-next)
- [Qwen3.7-Max](https://opper.ai/alibaba/qwen3-7-max)
